Quick Start — Get Extracting in Minutes

Overview

Get up and running with DocRouter in minutes. This guide walks you through the complete workflow from setup to automation. DocRouter transforms your document processing workflow through these key steps:

  • Step 1 - Create a tag and a prompt
  • Step 2 - Upload your first document with the tag
  • Step 3 - See automatic extraction results
  • Step 4 - Prompt Engineering to improve extraction quality
  • Step 5 - Manual Automation using bulk actions
  • Step 6 - Full Automation with REST API or Python SDK

Documents You Will Need

PDF
Sample Document - A homeowners insurance application form
Acord80_Homeowners_App.pdf
TXT
Sample Prompt - Prompt to extract fields from insurance form
acord_clearance_search_prompt.txt
JSON
Sample Schema - Schema for structured output
acord_clearance_search_schema.json
Quick Start Progress Step 1 of 6
Step 1 Create a Tag and a Prompt

We'll set up tags and prompts first so your documents process automatically upon upload.

1. Create a Tag

  1. Go to Tags in the left sidebar.
  2. Click Create Tag.
  3. Enter a descriptive name (e.g., invoice).
  4. Click Save tag.
Create Tag dialog

2. Create a Prompt

  1. Go to Prompts in the left sidebar.
  2. Click Create Prompt.
  3. Enter a name and instructions for the AI.
  4. Crucial: Assign the tag you just created.
  5. Click Save prompt.
Create Prompt screen
Step 2 Upload Your First Document

Now, upload a file and apply the tag to trigger the prompt.

Manual Upload with Tag

  1. Click "Upload Document".
  2. Select your file.
  3. In the Tags dropdown, select the tag you created in Step 1.
  4. Click Continue.
Upload Documents screen
Step 3 See Automatic Extraction Results

Wait for processing to complete and view your data.

Review Extractions

  1. Wait for status llm_completed.
  2. Click the document name.
  3. Go to the Extractions tab to see structured data.
Extractions results view
Step 4 Prompt Engineering

We'll refine our prompts to get better and more accurate results.

Extract the following information from this invoice:
- Invoice number
- Invoice date (format: YYYY-MM-DD)
- Vendor/supplier name
- Total amount
- All line items with descriptions, quantities, unit prices, and totals

Format the response as JSON matching the provided schema.
Be precise with numbers and dates.

Testing and Iteration

  1. Test with sample documents
  2. Review extracted data quality
  3. Refine schema and prompts
  4. Repeat until accuracy meets requirements
Step 5 Manual Automation

We'll process multiple documents at once to handle larger volumes.

Upload pre-tagged documents at scale

  1. Setting the document tag at upload time
  2. Prompts matching the tag will run automatically.
Bulk upload with tags assigned

Upload many files at once and apply tags so prompts run automatically.

Update prompts and re-run on documents at scale

  1. Open the Documents list and filter by the tag used by your prompt.
  2. Click Actions → Run LLM.
  3. Select the updated prompt and confirm to run across all filtered documents.
  4. Monitor progress; re-run as you iterate on prompt or schema.
Bulk actions to run prompt on many documents

Use bulk Actions to apply an updated prompt to many documents at once.

Step 6 Full Automation with APIs

We'll connect DocRouter to your systems for fully automated processing.

REST API Automation

DocRouter provides REST endpoints for automated document processing. Here are the key operations:

1. Upload Documents with Tags

# Upload documents with tags for automatic processing
curl -X POST https://api.docrouter.ai/v0/orgs/YOUR_ORG_ID/documents \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "documents": [{
      "name": "fi.pdf",
      "content": "BASE64_ENCODED_CONTENT",
      "tag_ids": ["invoice_tag_id"],
      "metadata": {"source": "api_upload"}
    }]
  }'

2. List Documents and Check Status

# List documents with filtering
curl -X GET "https://api.docrouter.ai/v0/orgs/YOUR_ORG_ID/documents?skip=0&limit=10" \
  -H "Authorization: Bearer YOUR_API_KEY"

# Get specific document details
curl -X GET https://api.docrouter.ai/v0/orgs/YOUR_ORG_ID/documents/DOCUMENT_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

3. Retrieve Extraction Results

# Get LLM extraction results (wait for state: "llm_completed")
curl -X GET https://api.docrouter.ai/v0/orgs/YOUR_ORG_ID/llm/result/DOCUMENT_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

# Download all results for a document
curl -X GET https://api.docrouter.ai/v0/orgs/YOUR_ORG_ID/llm/results/DOCUMENT_ID/download \
  -H "Authorization: Bearer YOUR_API_KEY"

Document Processing States:

  • uploaded: Document uploaded, OCR pending
  • ocr_processing: OCR in progress
  • ocr_completed: OCR complete, LLM processing pending
  • llm_processing: LLM extraction in progress
  • llm_completed: All processing complete, results available
  • llm_failed: Processing failed

For more details, see - REST API Documentation.

Python SDK Automation

Refer to the Python SDK Reference.

Learn More

  • Tags — Required routing mechanism that connects uploads to prompts
  • Prompts — Author extraction instructions for your documents
  • Schemas — Define structured JSON output for extractions
  • Document Agent - Configure schemas, tags, and prompts with AI
  • Knowledge Bases — Add reference context and power Knowledge Base Chat
  • Knowledge Base Chat — Chat over your knowledge bases